20 files changed, 276 insertions, 87 deletions

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index fbad8dfbb186..5d74a30fe00f 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -46,6 +46,7 @@
 struct annotation_options annotation__default_options = {
 	.use_offset     = true,
 	.jump_arrows    = true,
+	.offset_level	= ANNOTATION__OFFSET_JUMP_TARGETS,
 };
 
 const char 	*disassembler_style;
@@ -1262,6 +1263,9 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 				max_percent = sample->percent;
 		}
 
+		if (al->samples_nr > nr_percent)
+			nr_percent = al->samples_nr;
+
 		if (max_percent < min_pcnt)
 			return -1;
 
@@ -2512,7 +2516,8 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		if (!notes->options->use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
 		} else {
-			if (al->jump_sources) {
+			if (al->jump_sources &&
+			    notes->options->offset_level >= ANNOTATION__OFFSET_JUMP_TARGETS) {
 				if (notes->options->show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
@@ -2523,9 +2528,14 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 					obj__printf(obj, bf);
 					obj__set_color(obj, prev);
 				}
-
+print_addr:
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
 						    notes->widths.target, addr);
+			} else if (ins__is_call(&disasm_line(al)->ins) &&
+				   notes->options->offset_level >= ANNOTATION__OFFSET_CALL) {
+				goto print_addr;
+			} else if (notes->options->offset_level == ANNOTATION__MAX_OFFSET_LEVEL) {
+				goto print_addr;
 			} else {
 				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
 						    notes->widths.addr, " ");
@@ -2642,10 +2652,11 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
  */
 static struct annotation_config {
 	const char *name;
-	bool *value;
+	void *value;
 } annotation__configs[] = {
 	ANNOTATION__CFG(hide_src_code),
 	ANNOTATION__CFG(jump_arrows),
+	ANNOTATION__CFG(offset_level),
 	ANNOTATION__CFG(show_linenr),
 	ANNOTATION__CFG(show_nr_jumps),
 	ANNOTATION__CFG(show_nr_samples),
@@ -2677,8 +2688,16 @@ static int annotation__config(const char *var, const char *value,
 
 	if (cfg == NULL)
 		pr_debug("%s variable unknown, ignoring...", var);
-	else
-		*cfg->value = perf_config_bool(name, value);
+	else if (strcmp(var, "annotate.offset_level") == 0) {
+		perf_config_int(cfg->value, name, value);
+
+		if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
+			*(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
+		else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
+			*(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
+	} else {
+		*(bool *)cfg->value = perf_config_bool(name, value);
+	}
 	return 0;
 }
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index db8d09bea07e..f28a9e43421d 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -70,8 +70,17 @@ struct annotation_options {
 	     show_nr_jumps,
 	     show_nr_samples,
 	     show_total_period;
+	u8   offset_level;
 };
 
+enum {
+	ANNOTATION__OFFSET_JUMP_TARGETS = 1,
+	ANNOTATION__OFFSET_CALL,
+	ANNOTATION__MAX_OFFSET_LEVEL,
+};
+
+#define ANNOTATION__MIN_OFFSET_LEVEL ANNOTATION__OFFSET_JUMP_TARGETS
+
 extern struct annotation_options annotation__default_options;
 
 struct annotation;
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index af7ad814b2c3..cee658733e2c 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
 	}
 
 	obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
-	if (IS_ERR(obj)) {
+	if (IS_ERR_OR_NULL(obj)) {
 		pr_debug("bpf: failed to load buffer\n");
 		return ERR_PTR(-EINVAL);
 	}
@@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
 			pr_debug("bpf: successfull builtin compilation\n");
 		obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
 
-		if (!IS_ERR(obj) && llvm_param.dump_obj)
+		if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
 			llvm__dump_obj(filename, obj_buf, obj_buf_sz);
 
 		free(obj_buf);
 	} else
 		obj = bpf_object__open(filename);
 
-	if (IS_ERR(obj)) {
+	if (IS_ERR_OR_NULL(obj)) {
 		pr_debug("bpf: failed to load %s\n", filename);
 		return obj;
 	}
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 640af88331b4..4d5fc374e730 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * SPDX-License-Identifier: GPL-2.0
- *
  * Copyright(C) 2015-2018 Linaro Limited.
  *
  * Author: Tor Jeremiassen <tor@ti.com>
@@ -97,11 +96,19 @@ int cs_etm_decoder__get_packet(struct cs_etm_decoder *decoder,
 	/* Nothing to do, might as well just return */
 	if (decoder->packet_count == 0)
 		return 0;
+	/*
+	 * The queueing process in function cs_etm_decoder__buffer_packet()
+	 * increments the tail *before* using it.  This is somewhat counter
+	 * intuitive but it has the advantage of centralizing tail management
+	 * at a single location.  Because of that we need to follow the same
+	 * heuristic with the head, i.e we increment it before using its
+	 * value.  Otherwise the first element of the packet queue is not
+	 * used.
+	 */
+	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
 
 	*packet = decoder->packet_buffer[decoder->head];
 
-	decoder->head = (decoder->head + 1) & (MAX_BUFFER - 1);
-
 	decoder->packet_count--;
 
 	return 1;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 1b0d422373be..bf16dc9ee507 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -1,6 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * SPDX-License-Identifier: GPL-2.0
- *
  * Copyright(C) 2015-2018 Linaro Limited.
  *
  * Author: Tor Jeremiassen <tor@ti.com>
@@ -240,6 +239,7 @@ static void cs_etm__free(struct perf_session *session)
 	for (i = 0; i < aux->num_cpu; i++)
 		zfree(&aux->metadata[i]);
 
+	thread__zput(aux->unknown_thread);
 	zfree(&aux->metadata);
 	zfree(&aux);
 }
@@ -613,8 +613,8 @@ cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
 	return buff->len;
 }
 
-static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
-				     struct auxtrace_queue *queue)
+static void cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
+				    struct auxtrace_queue *queue)
 {
 	struct cs_etm_queue *etmq = queue->priv;
 
@@ -1358,6 +1358,23 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 	etm->auxtrace.free = cs_etm__free;
 	session->auxtrace = &etm->auxtrace;
 
+	etm->unknown_thread = thread__new(999999999, 999999999);
+	if (!etm->unknown_thread)
+		goto err_free_queues;
+
+	/*
+	 * Initialize list node so that at thread__zput() we can avoid
+	 * segmentation fault at list_del_init().
+	 */
+	INIT_LIST_HEAD(&etm->unknown_thread->node);
+
+	err = thread__set_comm(etm->unknown_thread, "unknown", 0);
+	if (err)
+		goto err_delete_thread;
+
+	if (thread__init_map_groups(etm->unknown_thread, etm->machine))
+		goto err_delete_thread;
+
 	if (dump_trace) {
 		cs_etm__print_auxtrace_info(auxtrace_info->priv, num_cpu);
 		return 0;
@@ -1372,16 +1389,18 @@ int cs_etm__process_auxtrace_info(union perf_event *event,
 
 	err = cs_etm__synth_events(etm, session);
 	if (err)
-		goto err_free_queues;
+		goto err_delete_thread;
 
 	err = auxtrace_queues__process_index(&etm->queues, session);
 	if (err)
-		goto err_free_queues;
+		goto err_delete_thread;
 
 	etm->data_queued = etm->queues.populated;
 
 	return 0;
 
+err_delete_thread:
+	thread__zput(etm->unknown_thread);
 err_free_queues:
 	auxtrace_queues__free(&etm->queues);
 	session->auxtrace = NULL;
diff --git a/tools/perf/util/cs-etm.h b/tools/perf/util/cs-etm.h
index 5864d5dca616..37f8d48179ca 100644
--- a/tools/perf/util/cs-etm.h
+++ b/tools/perf/util/cs-etm.h
@@ -1,18 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright(C) 2015 Linaro Limited. All rights reserved.
  * Author: Mathieu Poirier <mathieu.poirier@linaro.org>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published by
- * the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
 #ifndef INCLUDE__UTIL_PERF_CS_ETM_H__
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index f0a6cbd033cc..98ff3a6a3d50 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -1421,7 +1421,9 @@ size_t perf_event__fprintf_itrace_start(union perf_event *event, FILE *fp)
 size_t perf_event__fprintf_switch(union perf_event *event, FILE *fp)
 {
 	bool out = event->header.misc & PERF_RECORD_MISC_SWITCH_OUT;
-	const char *in_out = out ? "OUT" : "IN ";
+	const char *in_out = !out ? "IN         " :
+		!(event->header.misc & PERF_RECORD_MISC_SWITCH_OUT_PREEMPT) ?
+				    "OUT        " : "OUT preempt";
 
 	if (event->header.type == PERF_RECORD_SWITCH)
 		return fprintf(fp, " %s\n", in_out);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1ac8d9236efd..4cd2cf93f726 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -930,8 +930,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 	 * than leader in case leader 'leads' the sampling.
 	 */
 	if ((leader != evsel) && leader->sample_read) {
-		attr->sample_freq   = 0;
-		attr->sample_period = 0;
+		attr->freq           = 0;
+		attr->sample_freq    = 0;
+		attr->sample_period  = 0;
+		attr->write_backward = 0;
+		attr->sample_id_all  = 0;
 	}
 
 	if (opts->no_samples)
@@ -1922,7 +1925,8 @@ try_fallback:
 		goto fallback_missing_features;
 	} else if (!perf_missing_features.group_read &&
 		    evsel->attr.inherit &&
-		   (evsel->attr.read_format & PERF_FORMAT_GROUP)) {
+		   (evsel->attr.read_format & PERF_FORMAT_GROUP) &&
+		   perf_evsel__is_group_leader(evsel)) {
 		perf_missing_features.group_read = true;
 		pr_debug2("switching off group read\n");
 		goto fallback_missing_features;
@@ -2754,8 +2758,14 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err,
 		   (paranoid = perf_event_paranoid()) > 1) {
 		const char *name = perf_evsel__name(evsel);
 		char *new_name;
+		const char *sep = ":";
 
-		if (asprintf(&new_name, "%s%su", name, strchr(name, ':') ? "" : ":") < 0)
+		/* Is there already the separator in the name. */
+		if (strchr(name, '/') ||
+		    strchr(name, ':'))
+			sep = "";
+
+		if (asprintf(&new_name, "%s%su", name, sep) < 0)
 			return false;
 
 		if (evsel->name)
@@ -2870,8 +2880,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 #if defined(__i386__) || defined(__x86_64__)
 		if (evsel->attr.type == PERF_TYPE_HARDWARE)
 			return scnprintf(msg, size, "%s",
-	"No hardware sampling interrupt available.\n"
-	"No APIC? If so then you can boot the kernel with the \"lapic\" boot parameter to force-enable it.");
+	"No hardware sampling interrupt available.\n");
 #endif
 		break;
 	case EBUSY:
@@ -2894,8 +2903,7 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 
 	return scnprintf(msg, size,
 	"The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n"
-	"/bin/dmesg may provide additional information.\n"
-	"No CONFIG_PERF_EVENTS=y kernel support configured?",
+	"/bin/dmesg | grep -i perf may provide additional information.\n",
 			 err, str_error_r(err, sbuf, sizeof(sbuf)),
 			 perf_evsel__name(evsel));
 }
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d3ee3af618ef..b13f5f234c8f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -115,6 +115,7 @@ struct perf_evsel {
 	unsigned int		sample_size;
 	int			id_pos;
 	int			is_pos;
+	bool			uniquified_name;
 	bool			snapshot;
 	bool 			supported;
 	bool 			needs_swap;
@@ -126,6 +127,7 @@ struct perf_evsel {
 	bool			precise_max;
 	bool			ignore_missing_thread;
 	bool			forced_leader;
+	bool			use_uncore_alias;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
diff --git a/tools/perf/util/generate-cmdlist.sh b/tools/perf/util/generate-cmdlist.sh
index ff17920a5ebc..c3cef36d4176 100755
--- a/tools/perf/util/generate-cmdlist.sh
+++ b/tools/perf/util/generate-cmdlist.sh
@@ -38,7 +38,7 @@ do
 done
 echo "#endif /* HAVE_LIBELF_SUPPORT */"
 
-echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE)"
+echo "#if defined(HAVE_LIBAUDIT_SUPPORT) || defined(HAVE_SYSCALL_TABLE_SUPPORT)"
 sed -n -e 's/^perf-\([^ 	]*\)[ 	].* audit*/\1/p' command-list.txt |
 sort |
 while read cmd
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 121df1683c36..a8bff2178fbc 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1320,7 +1320,8 @@ static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
 
 	dir = opendir(path);
 	if (!dir) {
-		pr_warning("failed: can't open node sysfs data\n");
+		pr_debug2("%s: could't read %s, does this arch have topology information?\n",
+			  __func__, path);
 		return -1;
 	}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 2eca8478e24f..32d50492505d 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1019,13 +1019,6 @@ int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
 	return ret;
 }
 
-static void map_groups__fixup_end(struct map_groups *mg)
-{
-	int i;
-	for (i = 0; i < MAP__NR_TYPES; ++i)
-		__map_groups__fixup_end(mg, i);
-}
-
 static char *get_kernel_version(const char *root_dir)
 {
 	char version[PATH_MAX];
@@ -1233,6 +1226,7 @@ int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
 	const char *name = NULL;
+	struct map *map;
 	u64 addr = 0;
 	int ret;
 
@@ -1259,13 +1253,25 @@ int machine__create_kernel_maps(struct machine *machine)
 			machine__destroy_kernel_maps(machine);
 			return -1;
 		}
-		machine__set_kernel_mmap(machine, addr, 0);
+
+		/* we have a real start address now, so re-order the kmaps */
+		map = machine__kernel_map(machine);
+
+		map__get(map);
+		map_groups__remove(&machine->kmaps, map);
+
+		/* assume it's the last in the kmaps */
+		machine__set_kernel_mmap(machine, addr, ~0ULL);
+
+		map_groups__insert(&machine->kmaps, map);
+		map__put(map);
 	}
 
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(&machine->kmaps);
+	/* update end address of the kernel map using adjacent module address */
+	map = map__next(machine__kernel_map(machine));
+	if (map)
+		machine__set_kernel_mmap(machine, addr, map->start);
+
 	return 0;
 }
 
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 2fb0272146d8..2fc4ee8b86c1 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1219,13 +1219,16 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
-			 struct list_head *head_config, bool auto_merge_stats)
+			 struct list_head *head_config,
+			 bool auto_merge_stats,
+			 bool use_alias)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
 	struct perf_pmu *pmu;
 	struct perf_evsel *evsel;
 	struct parse_events_error *err = parse_state->error;
+	bool use_uncore_alias;
 	LIST_HEAD(config_terms);
 
 	pmu = perf_pmu__find(name);
@@ -1244,11 +1247,14 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		memset(&attr, 0, sizeof(attr));
 	}
 
+	use_uncore_alias = (pmu->is_uncore && use_alias);
+
 	if (!head_config) {
 		attr.type = pmu->type;
 		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
 		if (evsel) {
 			evsel->pmu_name = name;
+			evsel->use_uncore_alias = use_uncore_alias;
 			return 0;
 		} else {
 			return -ENOMEM;
@@ -1282,6 +1288,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel->metric_expr = info.metric_expr;
 		evsel->metric_name = info.metric_name;
 		evsel->pmu_name = name;
+		evsel->use_uncore_alias = use_uncore_alias;
 	}
 
 	return evsel ? 0 : -ENOMEM;
@@ -1317,7 +1324,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 				list_add_tail(&term->list, head);
 
 				if (!parse_events_add_pmu(parse_state, list,
-							  pmu->name, head, true)) {
+							  pmu->name, head,
+							  true, true)) {
 					pr_debug("%s -> %s/%s/\n", str,
 						 pmu->name, alias->str);
 					ok++;
@@ -1339,7 +1347,120 @@ int parse_events__modifier_group(struct list_head *list,
 	return parse_events__modifier_event(list, event_mod, true);
 }
 
-void parse_events__set_leader(char *name, struct list_head *list)
+/*
+ * Check if the two uncore PMUs are from the same uncore block
+ * The format of the uncore PMU name is uncore_#blockname_#pmuidx
+ */
+static bool is_same_uncore_block(const char *pmu_name_a, const char *pmu_name_b)
+{
+	char *end_a, *end_b;
+
+	end_a = strrchr(pmu_name_a, '_');
+	end_b = strrchr(pmu_name_b, '_');
+
+	if (!end_a || !end_b)
+		return false;
+
+	if ((end_a - pmu_name_a) != (end_b - pmu_name_b))
+		return false;
+
+	return (strncmp(pmu_name_a, pmu_name_b, end_a - pmu_name_a) == 0);
+}
+
+static int
+parse_events__set_leader_for_uncore_aliase(char *name, struct list_head *list,
+					   struct parse_events_state *parse_state)
+{
+	struct perf_evsel *evsel, *leader;
+	uintptr_t *leaders;
+	bool is_leader = true;
+	int i, nr_pmu = 0, total_members, ret = 0;
+
+	leader = list_first_entry(list, struct perf_evsel, node);
+	evsel = list_last_entry(list, struct perf_evsel, node);
+	total_members = evsel->idx - leader->idx + 1;
+
+	leaders = calloc(total_members, sizeof(uintptr_t));
+	if (WARN_ON(!leaders))
+		return 0;
+
+	/*
+	 * Going through the whole group and doing sanity check.
+	 * All members must use alias, and be from the same uncore block.
+	 * Also, storing the leader events in an array.
+	 */
+	__evlist__for_each_entry(list, evsel) {
+
+		/* Only split the uncore group which members use alias */
+		if (!evsel->use_uncore_alias)
+			goto out;
+
+		/* The events must be from the same uncore block */
+		if (!is_same_uncore_block(leader->pmu_name, evsel->pmu_name))
+			goto out;
+
+		if (!is_leader)
+			continue;
+		/*
+		 * If the event's PMU name starts to repeat, it must be a new
+		 * event. That can be used to distinguish the leader from
+		 * other members, even they have the same event name.
+		 */
+		if ((leader != evsel) && (leader->pmu_name == evsel->pmu_name)) {
+			is_leader = false;
+			continue;
+		}
+		/* The name is always alias name */
+		WARN_ON(strcmp(leader->name, evsel->name));
+
+		/* Store the leader event for each PMU */
+		leaders[nr_pmu++] = (uintptr_t) evsel;
+	}
+
+	/* only one event alias */
+	if (nr_pmu == total_members) {
+		parse_state->nr_groups--;
+		goto handled;
+	}
+
+	/*
+	 * An uncore event alias is a joint name which means the same event
+	 * runs on all PMUs of a block.
+	 * Perf doesn't support mixed events from different PMUs in the same
+	 * group. The big group has to be split into multiple small groups
+	 * which only include the events from the same PMU.
+	 *
+	 * Here the uncore event aliases must be from the same uncore block.
+	 * The number of PMUs must be same for each alias. The number of new
+	 * small groups equals to the number of PMUs.
+	 * Setting the leader event for corresponding members in each group.
+	 */
+	i = 0;
+	__evlist__for_each_entry(list, evsel) {
+		if (i >= nr_pmu)
+			i = 0;
+		evsel->leader = (struct perf_evsel *) leaders[i++];
+	}
+
+	/* The number of members and group name are same for each group */
+	for (i = 0; i < nr_pmu; i++) {
+		evsel = (struct perf_evsel *) leaders[i];
+		evsel->nr_members = total_members / nr_pmu;
+		evsel->group_name = name ? strdup(name) : NULL;
+	}
+
+	/* Take the new small groups into account */
+	parse_state->nr_groups += nr_pmu - 1;
+
+handled:
+	ret = 1;
+out:
+	free(leaders);
+	return ret;
+}
+
+void parse_events__set_leader(char *name, struct list_head *list,
+			      struct parse_events_state *parse_state)
 {
 	struct perf_evsel *leader;
 
@@ -1348,6 +1469,9 @@ void parse_events__set_leader(char *name, struct list_head *list)
 		return;
 	}
 
+	if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
+		return;
+
 	__perf_evlist__set_leader(list);
 	leader = list_entry(list->next, struct perf_evsel, node);
 	leader->group_name = name ? strdup(name) : NULL;
@@ -1715,7 +1839,7 @@ int parse_events(struct perf_evlist *evlist, const char *str,
 		struct perf_evsel *last;
 
 		if (list_empty(&parse_state.list)) {
-			WARN_ONCE(true, "WARNING: event parser found nothing");
+			WARN_ONCE(true, "WARNING: event parser found nothing\n");
 			return -1;
 		}
 
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 5015cfd58277..4473dac27aee 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -167,7 +167,9 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
-			 struct list_head *head_config, bool auto_merge_stats);
+			 struct list_head *head_config,
+			 bool auto_merge_stats,
+			 bool use_alias);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str,
@@ -178,7 +180,8 @@ int parse_events_copy_term_list(struct list_head *old,
 
 enum perf_pmu_event_symbol_type
 perf_pmu__parse_check(const char *name);
-void parse_events__set_leader(char *name, struct list_head *list);
+void parse_events__set_leader(char *name, struct list_head *list,
+			      struct parse_events_state *parse_state);
 void parse_events_update_lists(struct list_head *list_event,
 			       struct list_head *list_all);
 void parse_events_evlist_error(struct parse_events_state *parse_state,
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 7afeb80cc39e..e37608a87dba 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -161,7 +161,7 @@ PE_NAME '{' events '}'
 	struct list_head *list = $3;
 
 	inc_group_count(list, _parse_state);
-	parse_events__set_leader($1, list);
+	parse_events__set_leader($1, list, _parse_state);
 	$$ = list;
 }
 |
@@ -170,7 +170,7 @@ PE_NAME '{' events '}'
 	struct list_head *list = $2;
 
 	inc_group_count(list, _parse_state);
-	parse_events__set_leader(NULL, list);
+	parse_events__set_leader(NULL, list, _parse_state);
 	$$ = list;
 }
 
@@ -232,7 +232,7 @@ PE_NAME opt_event_config
 		YYABORT;
 
 	ALLOC_LIST(list);
-	if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) {
+	if (parse_events_add_pmu(_parse_state, list, $1, $2, false, false)) {
 		struct perf_pmu *pmu = NULL;
 		int ok = 0;
 		char *pattern;
@@ -251,7 +251,7 @@ PE_NAME opt_event_config
 					free(pattern);
 					YYABORT;
 				}
-				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true))
+				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true, false))
 					ok++;
 				parse_events_terms__delete(terms);
 			}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 064bdcb7bd78..d2fb597c9a8c 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -539,9 +539,10 @@ static bool pmu_is_uncore(const char *name)
 
 /*
  *  PMU CORE devices have different name other than cpu in sysfs on some
- *  platforms. looking for possible sysfs files to identify as core device.
+ *  platforms.
+ *  Looking for possible sysfs files to identify the arm core device.
  */
-static int is_pmu_core(const char *name)
+static int is_arm_pmu_core(const char *name)
 {
 	struct stat st;
 	char path[PATH_MAX];
@@ -550,18 +551,18 @@ static int is_pmu_core(const char *name)
 	if (!sysfs)
 		return 0;
 
-	/* Look for cpu sysfs (x86 and others) */
-	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/cpu", sysfs);
-	if ((stat(path, &st) == 0) &&
-			(strncmp(name, "cpu", strlen("cpu")) == 0))
-		return 1;
-
 	/* Look for cpu sysfs (specific to arm) */
 	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/cpus",
 				sysfs, name);
 	if (stat(path, &st) == 0)
 		return 1;
 
+	/* Look for cpu sysfs (specific to s390) */
+	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
+		  sysfs, name);
+	if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
+		return 1;
+
 	return 0;
 }
 
@@ -580,7 +581,7 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
  * cpuid string generated on this platform.
  * Otherwise return non-zero.
  */
-int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
 {
 	regex_t re;
 	regmatch_t pmatch[1];
@@ -662,6 +663,7 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 	struct pmu_events_map *map;
 	struct pmu_event *pe;
 	const char *name = pmu->name;
+	const char *pname;
 
 	map = perf_pmu__find_map(pmu);
 	if (!map)
@@ -680,11 +682,9 @@ static void pmu_add_cpu_aliases(struct list_head *head, struct perf_pmu *pmu)
 			break;
 		}
 
-		if (!is_pmu_core(name)) {
-			/* check for uncore devices */
-			if (pe->pmu == NULL)
-				continue;
-			if (strncmp(pe->pmu, name, strlen(pe->pmu)))
+		if (!is_arm_pmu_core(name)) {
+			pname = pe->pmu ? pe->pmu : "cpu";
+			if (strncmp(pname, name, strlen(pname)))
 				continue;
 		}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 10dd5fce082b..7f8afacd08ee 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -531,6 +531,8 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 			PyLong_FromUnsignedLongLong(sample->period));
 	pydict_set_item_string_decref(dict_sample, "phys_addr",
 			PyLong_FromUnsignedLongLong(sample->phys_addr));
+	pydict_set_item_string_decref(dict_sample, "addr",
+			PyLong_FromUnsignedLongLong(sample->addr));
 	set_sample_read_in_dict(dict_sample, sample, evsel);
 	pydict_set_item_string_decref(dict, "sample", dict_sample);
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 62b2dd2253eb..1466814ebada 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -2091,16 +2091,14 @@ static bool symbol__read_kptr_restrict(void)
 
 int symbol__annotation_init(void)
 {
+	if (symbol_conf.init_annotation)
+		return 0;
+
 	if (symbol_conf.initialized) {
 		pr_err("Annotation needs to be init before symbol__init()\n");
 		return -1;
 	}
 
-	if (symbol_conf.init_annotation) {
-		pr_warning("Annotation being initialized multiple times\n");
-		return 0;
-	}
-
 	symbol_conf.priv_size += sizeof(struct annotation);
 	symbol_conf.init_annotation = true;
 	return 0;
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 895122d638dd..0ee7f568d60c 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -17,7 +17,7 @@
 #include <stdlib.h>
 #include <linux/compiler.h>
 
-#ifdef HAVE_SYSCALL_TABLE
+#ifdef HAVE_SYSCALL_TABLE_SUPPORT
 #include <string.h>
 #include "string2.h"
 #include "util.h"
@@ -139,7 +139,7 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g
 	return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
 }
 
-#else /* HAVE_SYSCALL_TABLE */
+#else /* HAVE_SYSCALL_TABLE_SUPPORT */
 
 #include <libaudit.h>
 
@@ -176,4 +176,4 @@ int syscalltbl__strglobmatch_first(struct syscalltbl *tbl, const char *syscall_g
 {
 	return syscalltbl__strglobmatch_next(tbl, syscall_glob, idx);
 }
-#endif /* HAVE_SYSCALL_TABLE */
+#endif /* HAVE_SYSCALL_TABLE_SUPPORT */
diff --git a/tools/perf/util/trace-event-scripting.c b/tools/perf/util/trace-event-scripting.c
index 0ac9077f62a2..b1e5c3a2b8e3 100644
--- a/tools/perf/util/trace-event-scripting.c
+++ b/tools/perf/util/trace-event-scripting.c
@@ -98,7 +98,7 @@ static void register_python_scripting(struct scripting_ops *scripting_ops)
 	}
 }
 
-#ifdef NO_LIBPYTHON
+#ifndef HAVE_LIBPYTHON_SUPPORT
 void setup_python_scripting(void)
 {
 	register_python_scripting(&python_scripting_unsupported_ops);
@@ -161,7 +161,7 @@ static void register_perl_scripting(struct scripting_ops *scripting_ops)
 	}
 }
 
-#ifdef NO_LIBPERL
+#ifndef HAVE_LIBPERL_SUPPORT
 void setup_perl_scripting(void)
 {
 	register_perl_scripting(&perl_scripting_unsupported_ops);